initial version of the app

app.py

@@ -0,0 +1,138 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+
+# Initialize model and tokenizer
+MODEL_PATH = "gokul-pv/Llama-3.2-1B-Instruct-16bit-TeSO"
+
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_PATH,
+        torch_dtype=torch.float32,  # Use float32 for CPU
+        device_map="cpu"  # Ensure model runs on CPU
+    )
+    return model, tokenizer
+
+class CustomTextStreamer:
+    """Custom streamer that captures only the model's response"""
+    def __init__(self, tokenizer):
+        self.tokenizer = tokenizer
+        self.generated_text = []
+        self.next_tokens_are_prompt = True
+        
+    def put(self, value):
+        if isinstance(value, torch.Tensor):
+            if len(value.shape) > 1:
+                value = value[0]
+            decoded_text = self.tokenizer.decode(value.tolist(), skip_special_tokens=True)
+        else:
+            decoded_text = value
+            
+        if self.next_tokens_are_prompt:
+            self.next_tokens_are_prompt = False  # Skip prompt tokens
+        else:
+            self.generated_text.append(decoded_text)
+            print(decoded_text, end="", flush=True)
+    
+    def end(self):
+        self.next_tokens_are_prompt = True
+        print("")
+    
+    def get_generated_text(self):
+        return "".join(self.generated_text)
+
+def analyze_architecture(code_input, temperature=1.5, max_tokens=512):
+    """
+    Analyze architecture code using the loaded model
+    """
+    model, tokenizer = load_model()
+    
+    messages = [
+        {
+            "role": "system",
+            "content": "You are an expert in analyzing system architecture written using code. "
+                      "You check the architecture and provide clear and detailed explanations "
+                      "regarding how the architecture can be improved for better performance, "
+                      "scalability, maintainability, and cost-effectiveness. You also check "
+                      "for possible cybersecurity issues and if the components can be "
+                      "replaced with newer and better components."
+        },
+        {
+            "role": "user",
+            "content": code_input
+        }
+    ]
+    
+    # Tokenize input
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    ).to("cpu")  # Ensure tensors are on CPU
+    
+    # Initialize text streamer
+    text_streamer = CustomTextStreamer(tokenizer)
+    
+    # Generate response
+    with torch.inference_mode():
+        model.generate(
+            input_ids=inputs,
+            streamer=text_streamer,
+            max_new_tokens=max_tokens,
+            use_cache=True,
+            temperature=temperature,
+            min_p=0.1
+        )
+    
+    return text_streamer.get_generated_text()
+
+# Create Gradio interface
+def create_gradio_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("# Tech Stack Optimizer - TeSO")
+        
+        with gr.Row():
+            with gr.Column():
+                code_input = gr.Code(
+                    label="Input Architecture Code",
+                    language="python",
+                    lines=10
+                )
+                
+                with gr.Row():
+                    temperature = gr.Slider(
+                        minimum=0.1,
+                        maximum=2.0,
+                        value=1.5,
+                        label="Temperature"
+                    )
+                    max_tokens = gr.Slider(
+                        minimum=64,
+                        maximum=2048,
+                        value=512,
+                        step=64,
+                        label="Max Tokens"
+                    )
+                
+                submit_btn = gr.Button("Analyze Architecture")
+            
+            with gr.Column():
+                output = gr.Markdown(label="Analysis Results")
+        
+        submit_btn.click(
+            fn=analyze_architecture,
+            inputs=[code_input, temperature, max_tokens],
+            outputs=output
+        )
+    
+    return demo
+
+if __name__ == "__main__":
+    demo = create_gradio_interface()
+    demo.launch(
+        share=True,  # Enable sharing
+        server_name="0.0.0.0",  # Listen on all network interfaces
+        server_port=7860  # Default Gradio port
+    )

requirements.txt

@@ -0,0 +1,225 @@
+absl-py==2.1.0
+accelerate==1.3.0
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyascii==0.3.2
+anyio==4.8.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==3.0.0
+async-lru==2.0.4
+async-timeout==5.0.1
+attrs==24.3.0
+babel==2.16.0
+backoff==2.2.1
+beautifulsoup4==4.12.3
+bitsandbytes==0.45.2
+bleach==6.2.0
+boto3==1.36.3
+botocore==1.36.3
+cachetools==5.5.1
+certifi==2024.12.14
+cffi==1.17.1
+charset-normalizer==3.4.1
+click==8.1.8
+comm==0.2.2
+contourpy==1.3.1
+contractions==0.1.73
+cut-cross-entropy==25.1.1
+cycler==0.12.1
+datasets==3.2.0
+debugpy==1.8.12
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.8
+docstring_parser==0.16
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.6
+fastjsonschema==2.21.1
+ffmpy==0.5.0
+filelock==3.17.0
+fire==0.7.0
+fonttools==4.55.4
+fqdn==1.5.1
+frozenlist==1.5.0
+fsspec==2024.9.0
+google-auth==2.37.0
+google-auth-oauthlib==1.2.1
+gradio==5.16.0
+gradio_client==1.7.0
+grpcio==1.69.0
+h11==0.14.0
+hf_transfer==0.1.9
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.28.1
+idna==3.10
+ipykernel==6.26.0
+ipython==8.17.2
+ipywidgets==8.1.1
+isoduration==20.11.0
+jedi==0.19.2
+Jinja2==3.1.5
+jmespath==1.0.1
+joblib==1.4.2
+json5==0.10.0
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter-events==0.11.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.15.0
+jupyter_server_terminals==0.5.3
+jupyterlab==4.2.0
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.8
+lightning==2.5.0.post0
+lightning-cloud==0.5.70
+lightning-utilities==0.11.9
+lightning_sdk==0.1.49
+litdata==0.2.32
+litserve==0.2.6
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.1.0
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+nbclient==0.10.2
+nbconvert==7.16.5
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.4.2
+notebook_shim==0.2.4
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+orjson==3.10.15
+overrides==7.7.0
+packaging==24.2
+pandas==2.1.4
+pandocfilters==1.5.1
+parso==0.8.4
+peft==0.14.0
+pexpect==4.9.0
+pillow==11.1.0
+platformdirs==4.3.6
+prometheus_client==0.21.1
+prompt_toolkit==3.0.50
+propcache==0.2.1
+protobuf==3.20.3
+psutil==6.1.1
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyahocorasick==2.1.0
+pyarrow==19.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.10.5
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.19.1
+PyJWT==2.10.1
+pyparsing==3.2.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==3.2.1
+python-multipart==0.0.20
+pytorch-lightning==2.5.0.post0
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.36.1
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.9.4
+rpds-py==0.22.3
+rsa==4.9
+ruff==0.9.6
+s3transfer==0.11.1
+safehttpx==0.1.6
+safetensors==0.5.2
+scikit-learn==1.3.2
+scipy==1.11.4
+seaborn==0.13.2
+semantic-version==2.10.0
+Send2Trash==1.8.3
+sentencepiece==0.2.0
+shellingham==1.5.4
+shtab==1.7.1
+simple-term-menu==1.6.6
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.6
+stack-data==0.6.3
+starlette==0.41.3
+sympy==1.13.3
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+termcolor==2.5.0
+terminado==0.18.1
+textsearch==0.0.24
+threadpoolctl==3.5.0
+tinycss2==1.4.0
+tokenizers==0.21.0
+tomli==2.2.1
+tomlkit==0.13.2
+torch==2.2.1+cu121
+torchmetrics==1.3.1
+torchvision==0.17.1+cu121
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.48.1
+triton==2.2.0
+trl==0.8.6
+typeguard==4.4.1
+typer==0.15.1
+types-python-dateutil==2.9.0.20241206
+typing_extensions==4.12.2
+tyro==0.9.14
+tzdata==2025.1
+uri-template==1.3.0
+urllib3==2.3.0
+uvicorn==0.34.0
+uvloop==0.21.0
+watchfiles==1.0.4
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==14.2
+Werkzeug==3.1.3
+widgetsnbextension==4.0.13
+xformers==0.0.29
+xxhash==3.5.0
+yarl==1.18.3